mlsanityData to 7 Oct 2026

ALBench: A Framework for Evaluating Active Learning in Object Detection

arXiv 2207.13339 ↗First posted 27 Jul 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Active learning is an important technology for automated machine learning systems. In contrast to Neural Architecture Search (NAS) which aims at automating neural network architecture design, active learning aims at automating training data selection. It is especially critical for training a long-tailed task, in which positive samples are sparsely distributed. Active learning alleviates the expensive data annotation issue through incrementally training models powered with efficient data selection. Instead of annotating all unlabeled samples, it iteratively selects and annotates the most valuable samples. Active learning has been popular in image classification, but has not been fully explored in object detection. Most of current approaches on object detection are evaluated with different settings, making it difficult to fairly compare their performance. To facilitate the research in this field, this paper contributes an active learning benchmark framework named as ALBench for evaluating active learning in object detection. Developed on an automatic deep model training system, this ALBench framework is easy-to-use, compatible with different active learning algorithms, and ensures the same training and testing protocols. We hope this automated benchmark system help researchers to easily reproduce literature's performance and have objective comparisons with prior arts. The code will be release through Github.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 18 of its 24 references that are in the map. First posted on arXiv 27 Jul 2022.

Builds on

18 of 24 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  7. 2019Learning Loss for Active Learningcited by 335
  8. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  9. 2021Multiple instance active learning for object detectioncited by 77
  10. 2020Sequential Graph Convolutional Network for Active Learningcited by 69
  11. 2019Active Learning for Deep Detection Neural Networkscited by 62
  12. 2020Scalable Active Learning for Object Detectioncited by 58
6 more
  1. 2018Active Learning for Deep Object Detectioncited by 49
  2. 2018Localization-Aware Active Learning for Object Detectioncited by 48
  3. 2019Deep Active Learning for Efficient Training of a LiDAR 3D Object Detectorcited by 45
  4. 2021Consistency-based Active Learning for Object Detectioncited by 32
  5. 2016Crowdsourcing in Computer Visioncited by 31
  6. 2021YMIR: A Rapid Data-centric Development Platform for Vision Applicationscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 0; 2024: 1; 2025: 2; 2026: 1.

6 papers.

  1. 2024Computer Vision for Primate Behavior Analysis in the Wildcited by 10
  2. 2022Deep Active Learning for Computer Vision: Past and Futurecited by 7
  3. 2025Streamlining the Development of Active Learning Methods in Real-World Object Detectioncited by 2
  4. 2022Evaluating Zero-cost Active Learning for Object Detectioncited by 1
  5. 2025Active Learning Methods for Efficient Data Utilization and Model Performance Enhancementcited by 0
  6. 2026Distance to Class Prototypes: Active Learning for Object Detectioncited by 0